search

intel / auto-round

Advanced Quantization Algorithm for LLMs. This is official implementation of "Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs"
https://arxiv.org/abs/2309.05516
Apache License 2.0
132 stars 18 forks source link

example_bugfix #160

Closed WeiweiZhang1 closed 1 month ago

WeiweiZhang1 commented 1 month ago

add trust_remote_code for eval_042, example bugfix, enable amp quant_layer of cpu device

wenhuach21 commented 1 month ago

change the title